def extract(model, filepath, vid):
"""Extract features by inception_v3."""
# data loader for frames in ingle video
data_loader = get_dataloader(dataset="VideoFrame",
path=filepath,
num_frames=cfg.num_frames,
batch_size=cfg.batch_size)
# extract features by inception_v3
feats = None
for step, frames in enumerate(data_loader):
print("--> extract features [{}/{}]".format(step + 1,
len(data_loader)))
feat = model(make_variable(frames))
feats = concat_feat_var(feats, feat.data.cpu())
print("--> save feats to {}".format(
cfg.inception_v3_feats_path.format(vid)))
torch.save(feats, cfg.inception_v3_feats_path.format(vid))
print("--> delete original video file: {}".format(filepath))
os.remove(filepath)
if __name__ == '__main__':
# init models and data loader
model = make_cuda(
inception_v3(pretrained=True, transform_input=True, extract_feat=True))
pca = PCAWrapper(n_components=cfg.n_components)
model.eval()
# data loader for frames in ingle video
# data_loader = get_dataloader(dataset="VideoFrame",
# path=cfg.video_file,
# num_frames=cfg.num_frames,
# batch_size=cfg.batch_size)
# data loader for frames decoded from several videos
data_loader = get_dataloader(dataset="FrameImage",
path=cfg.frame_root,
batch_size=cfg.batch_size)
# extract features by inception_v3
feats = None
for step, frames in enumerate(data_loader):
print("extracting feature [{}/{}]".format(step + 1, len(data_loader)))
feat = model(make_variable(frames))
feats = concat_feat(feats, feat.data.cpu())
# recude dimensions by PCA
X = feats.numpy()
pca.fit(X)
X_ = pca.transform(X)
print("reduce X {} to X_ {}".format(X.shape, X_.shape))
from models import PCAWrapper, inception_v3
if __name__ == '__main__':
# init Inception v3 model
model = make_cuda(
inception_v3(pretrained=True, transform_input=True, extract_feat=True))
model.eval()
# init PCA model
pca = PCAWrapper(n_components=cfg.n_components,
batch_size=cfg.pca_batch_size)
pca.load_params(filepath=cfg.pca_model)
# data loader for frames in ingle video
data_loader = get_dataloader(dataset="VideoFrame",
path=cfg.video_file,
num_frames=cfg.num_frames,
batch_size=cfg.batch_size)
# init writer
writer = RecordWriter(filepath="data/test.tfrecord", level="frame")
# extract features by inception_v3
feats = None
for step, frames in enumerate(data_loader):
print("extracting feature [{}/{}]".format(step + 1, len(data_loader)))
feat = model(make_variable(frames))
feat_np = feat.data.cpu().numpy()
# recude dimensions by PCA
feat_ = pca.transform(feat_np)
feats = concat_feat(feats, feat_)
model_path=cfg.inception_v3_model,
transform_input=True,
extract_feat=True))
model.eval()
# init PCA model
pca = PCAWrapper(n_components=cfg.n_components,
batch_size=cfg.pca_batch_size)
pca.load_params(filepath=cfg.pca_model)
subfolders = list_folders(cfg.dataset_path)
for subfolder in subfolders:
print("current folder: {}".format(subfolder))
# data loader for frames in single video
data_loader = get_dataloader(dataset="FrameImage",
path=os.path.join(subfolder, 'frames'),
frame_num =cfg.frame_num,
batch_size=cfg.batch_size)
# extract features by inception_v3
feats = None
for step, frames in enumerate(data_loader):
#print("extracting feature [{}/{}]".format(step + 1, len(data_loader)))
feat = model(make_variable(frames))
feat_np = feat.data.cpu().numpy()
# recude dimensions by PCA
feat_ = pca.transform(feat_np)
feats = concat_feat(feats, feat_)
embedding = quantize(feats)
# write visual features into numpy file
np.save('{}.npy'.format(os.path.join(subfolder, 'vfeat')), embedding[:cfg.frame_num,])
